Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 4250 in Layer 25
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 7.8844. Min Range: -7.8844
Max Act: 7.8844. Min Act: -0.1700
Data Index: 5899877 (Open Web Text)
Max Activating Token Index: 878
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 7.8844. Min Range: -7.8844
Max Act: 7.6969. Min Act: -0.1700
Data Index: 7763603 (Open Web Text)
Max Activating Token Index: 821
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 7.8844. Min Range: -7.8844
Max Act: 7.7594. Min Act: -0.1700
Data Index: 7834884 (Open Web Text)
Max Activating Token Index: 345
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 7.8844. Min Range: -7.8844
Max Act: 7.5719. Min Act: -0.1700
Data Index: 8802405 (Open Web Text)
Max Activating Token Index: 19
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 7.8844. Min Range: -7.8844
Max Act: 7.5094. Min Act: -0.1700
Data Index: 2405065 (Open Web Text)
Max Activating Token Index: 28
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 7.8844. Min Range: -7.8844
Max Act: 7.5094. Min Act: -0.1700
Data Index: 7763604 (Open Web Text)
Max Activating Token Index: 987
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 7.8844. Min Range: -7.8844
Max Act: 7.4781. Min Act: -0.1700
Data Index: 7570073 (Open Web Text)
Max Activating Token Index: 505
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 7.8844. Min Range: -7.8844
Max Act: 7.3219. Min Act: -0.1700
Data Index: 8459446 (Open Web Text)
Max Activating Token Index: 86
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 7.8844. Min Range: -7.8844
Max Act: 7.2906. Min Act: -0.1700
Data Index: 6847228 (Open Web Text)
Max Activating Token Index: 351
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 7.8844. Min Range: -7.8844
Max Act: 7.3219. Min Act: -0.1700
Data Index: 1616728 (Open Web Text)
Max Activating Token Index: 902
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 7.8844. Min Range: -7.8844
Max Act: 7.3219. Min Act: -0.1700
Data Index: 5094100 (Open Web Text)
Max Activating Token Index: 200
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 7.8844. Min Range: -7.8844
Max Act: 7.2906. Min Act: -0.1700
Data Index: 7554177 (Open Web Text)
Max Activating Token Index: 576
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 7.8844. Min Range: -7.8844
Max Act: 7.2594. Min Act: -0.1700
Data Index: 4148401 (Open Web Text)
Max Activating Token Index: 227
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 7.8844. Min Range: -7.8844
Max Act: 7.2594. Min Act: -0.1700
Data Index: 7936661 (Open Web Text)
Max Activating Token Index: 919
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 7.8844. Min Range: -7.8844
Max Act: 7.2594. Min Act: -0.1700
Data Index: 8378621 (Open Web Text)
Max Activating Token Index: 486
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 7.8844. Min Range: -7.8844
Max Act: 7.1656. Min Act: -0.1700
Data Index: 5443743 (Open Web Text)
Max Activating Token Index: 762
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 7.8844. Min Range: -7.8844
Max Act: 7.0406. Min Act: -0.1700
Data Index: 3126371 (Open Web Text)
Max Activating Token Index: 287
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 7.8844. Min Range: -7.8844
Max Act: 7.0719. Min Act: -0.1700
Data Index: 7547706 (Open Web Text)
Max Activating Token Index: 971
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 7.8844. Min Range: -7.8844
Max Act: 6.9781. Min Act: -0.1700
Data Index: 8355284 (Open Web Text)
Max Activating Token Index: 860
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 7.8844. Min Range: -7.8844
Max Act: 6.9781. Min Act: -0.1700
Data Index: 4747591 (Open Web Text)
Max Activating Token Index: 446
Click toggle to see full text
Truncated
Full Text #19